Update `dataset_stats()` for HUB (#3536)

* Update `dataset_stats()` for HUB

Cleanup of b6fdd2e

* autodownload flag

* Update general.py

* cleanup

utils/datasets.py

@@ -1086,18 +1086,17 @@ def verify_image_label(params):
         return [None] * 4 + [nm, nf, ne, nc]
 
 
-def dataset_stats(path='data/coco128.yaml', verbose=False):
+def dataset_stats(path='coco128.yaml', autodownload=False, verbose=False):
     """ Return dataset statistics dictionary with images and instances counts per split per class
-    Usage: from utils.datasets import *; dataset_stats('data/coco128.yaml')
+    Usage: from utils.datasets import *; dataset_stats('coco128.yaml', verbose=True)
     Arguments
         path:           Path to data.yaml
+        autodownload:   Attempt to download dataset if not found locally
         verbose:        Print stats dictionary
     """
-    path = check_file(Path(path))
-    with open(path) as f:
+    with open(check_file(Path(path))) as f:
         data = yaml.safe_load(f)  # data dict
-    check_dataset(data)  # download dataset if missing
-
+    check_dataset(data, autodownload)  # download dataset if missing
     nc = data['nc']  # number of classes
     stats = {'nc': nc, 'names': data['names']}  # statistics dictionary
     for split in 'train', 'val', 'test':

utils/general.py

@@ -220,14 +220,14 @@ def check_file(file):
         return files[0]  # return file
 
 
-def check_dataset(dict):
+def check_dataset(data, autodownload=True):
     # Download dataset if not found locally
-    val, s = dict.get('val'), dict.get('download')
+    val, s = data.get('val'), data.get('download')
     if val and len(val):
         val = [Path(x).resolve() for x in (val if isinstance(val, list) else [val])]  # val path
         if not all(x.exists() for x in val):
             print('\nWARNING: Dataset not found, nonexistent paths: %s' % [str(x) for x in val if not x.exists()])
-            if s and len(s):  # download script
+            if s and len(s) and autodownload:  # download script
                 if s.startswith('http') and s.endswith('.zip'):  # URL
                     f = Path(s).name  # filename
                     print(f'Downloading {s} ...')